This paper will examine the effects of tax incentives for small businesseson employment level evaluating a program with this purpose implemented in Brazil in the 1990s. We first develop a theoretical framework which guides both the de nition of the parameters of interest and their identi cation. Selection problems both into the treatment group and into the data sampleare tackled by combining fi xed effects methods and regression discontinuity design on alternative sub-samples of a longitudinal database of manufacturing fi rms. The results show that on the one hand the size composition of thetreated fi rms may be changed due to the survival of some smaller fi rms that would have exited had it not been eligible to the program. On the other hand, the treated fi rms who do not depend on the program to survive do employ more workers.